Filters








8 Hits in 4.7 sec

GNetIc – Using Bayesian Decision Networks for Iconic Gesture Generation [chapter]

Kirsten Bergmann, Stefan Kopp
2009 Lecture Notes in Computer Science  
We present a framework, GNetIc, that combines data-driven with model-based techniques to model the generation of iconic gestures with Bayesian decision networks.  ...  This task is challenging as the mapping is determined by the visuo-spatial features of the referent, the overall discourse context as well as concomitant speech, and its outcome varies considerably across  ...  Acknowledgements This research is partially supported by the Deutsche Forschungsgemeinschaft (DFG) in the Collaborative Research Center 673 "Alignment in Communication" and the Center of Excellence in  ... 
doi:10.1007/978-3-642-04380-2_12 fatcat:w5d44xv3ynd4fe3tvupdb23hr4

Prosody based audiovisual coanalysis for coverbal gesture recognition

S. Kettebekov, M. Yeasin, R. Sharma
2005 IEEE transactions on multimedia  
A weighted fusion scheme is then proposed for combining the decisions of the two co-analysis models.  ...  The study aims to explore contributions of voluntary and involuntary factors of coverbal gesture production to synchronization patterns. The  ...  Bi-gram model of co-occurrence classes ( Figure 5) is modeled by causal dependency of ( 1) a i t ω − on ( ) a i t ω within the Bayesian network.  ... 
doi:10.1109/tmm.2004.840590 fatcat:47s5r2fyfnghnppvygz5krupae

Systematicity and Idiosyncrasy in Iconic Gesture Use: Empirical Analysis and Computational Modeling [chapter]

Kirsten Bergmann, Stefan Kopp
2010 Lecture Notes in Computer Science  
Based on this, a computational model of gesture formation is presented that combines data-based, probabilistic and model-based decision making.  ...  Why an iconic gesture takes its particular form is a largely open question, given the variations one finds across both situations and speakers.  ...  Acknowledgements This research is partially supported by the Deutsche Forschungsgemeinschaft (DFG) in the SFB 673 "Alignment in Communication" and the Center of Excellence in "Cognitive Interaction Technology  ... 
doi:10.1007/978-3-642-12553-9_16 fatcat:pua3i27xmva3badert3anyp6yy

Requirements and Building Blocks for Sociable Embodied Agents [chapter]

Stefan Kopp, Kirsten Bergmann, Hendrik Buschmeier, Amir Sadeghipour
2009 Lecture Notes in Computer Science  
We argue that this requires them to be capable of flexible multimodal expressiveness, incremental perception of other's behaviors, and the integration and interaction of these models in unified sensorimotor  ...  We present work on probabilistic models for these three requirements with a focus on gestural behavior.  ...  Acknowledgements This research is supported by the Deutsche Forschungsgemeinschaft (DFG) in the Collaborative Research Center 673 "Alignment in Communication" and the Center of Excellence in "Cognitive  ... 
doi:10.1007/978-3-642-04617-9_64 fatcat:abo66kygfbfbbp4ceaeav3equm

Social resonance and embodied coordination in face-to-face conversation with artificial interlocutors

Stefan Kopp
2010 Speech Communication  
Work on modeling this for ECAs with a focus on coverbal gestures is presented.  ...  It is argued that one major step in this direction is embodied coordination, mutual adaptations that are mediated by flexible modules for the top-down production and bottom-up perception of expressive  ...  This research is supported by the Deutsche Forschungsgemeinschaft (DFG) in SFB 673 "Alignment in Communication" and the Center of Excellence "Cognitive Interaction Technology" (CITEC).  ... 
doi:10.1016/j.specom.2010.02.007 fatcat:6mtne6qu2nd2hpgx3vrdfa2os4

Building Expression into Virtual Characters [article]

V. Vinayagamoorthy, M. Gillies, A. Steed, E. Tanguy, X. Pan, C. Loscos, M. Slater
2006 Eurographics State of the Art Reports  
We cover models of individual characters' emotion and personality, models of interpersonal behaviour and methods for generating expression.  ...  In particular, we assume that a virtual character representation is already available, and we describe a variety of models and methods that are used to give the characters more "depth" so that they are  ...  Breese and Ball [BB98] modelled agents' level and intensity of happiness with two personality traits (dominance and friendliness) in a Bayesian Belief Network (BBN) model.  ... 
doi:10.2312/egst.20061052 fatcat:hps7ewshhrdi3jbi5ros57lf2q

With diversity in mind: Freeing the language sciences from Universal Grammar

Nicholas Evans, Stephen C. Levinson
2009 Behavioral and Brain Sciences  
confront the diversity offered to us by the world's 6,000 to 8,000 languages.  ...  This target article summarizes decades of cross-linguistic work by typologists and descriptive linguists, showing just how few and unprofound the universal characteristics of language are, once we honestly  ...  whereas constraints on the production of hand or arm gestures are only relevant to manual sign.  ... 
doi:10.1017/s0140525x09990525 fatcat:pqieza6vancijg4vfnu7humrli

The myth of language universals: Language diversity and its importance for cognitive science

Nicholas Evans, Stephen C. Levinson
2009 Behavioral and Brain Sciences  
confront the diversity offered to us by the world's 6,000 to 8,000 languages.  ...  This target article summarizes decades of cross-linguistic work by typologists and descriptive linguists, showing just how few and unprofound the universal characteristics of language are, once we honestly  ...  , by voice, patterns of sound originally received by ear, technically known as vocal production learning (Janik & Slater 1997) .  ... 
doi:10.1017/s0140525x0999094x pmid:19857320 fatcat:mjf3lbg5e5c7rgz5gi5y3aif7y